Model comparison
Llama 4 Scout vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 2.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Meta
Mistral AISummary
- They share 21 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Mistral Large 3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 37.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 36.9% for Llama 4 Scout and 50.9% for Mistral Large 3.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Mistral Large 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 39.1 |
| Released | 2025-04-05 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.30 | $0.75 |
| Results tracked | 43 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Llama 4 Scout: 20.2 (#339), Mistral Large 3: 34.4 (#237)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1286 | 1448 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1230 |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Mistral Large 3: —
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Mistral Large 3 leads
Llama 4 Scout: 9.1 (#345), Mistral Large 3: 15.2 (#319)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 50.9% |
| LMArena Hard Prompts | 1266 | 1429 |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| Thematic Generalization | — | 23% |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Mistral Large 3 leads
Llama 4 Scout: 19.6 (#286), Mistral Large 3: 38.7 (#129)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1287 | 1414 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Mistral Large 3 leads
Llama 4 Scout: 31.9 (#217), Mistral Large 3: 36.0 (#177)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 7.7% | 14.5% |
| LMArena Expert | 1235 | 1421 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Mistral Large 3 leads
Llama 4 Scout: 32.2 (#102), Mistral Large 3: 38.2 (#66)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1118 | 1221 |
| SpatialViz-Bench | 34.2% | — |
Multilingual Mistral Large 3 leads
Llama 4 Scout: 41.0 (#212), Mistral Large 3: 52.5 (#84)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1252 | 1413 |
| LMArena Chinese | 1255 | 1447 |
| LMArena French | 1282 | 1455 |
| LMArena German | 1272 | 1437 |
| LMArena Japanese | 1206 | 1394 |
| LMArena Korean | 1207 | 1384 |
| LMArena Russian | 1263 | 1411 |
| LMArena Spanish | 1278 | 1440 |
Instruction Following Mistral Large 3 leads
Llama 4 Scout: 65.8 (#217), Mistral Large 3: 74.0 (#108)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1403 |
| IFEval | 81.8% | — |
Long Context Mistral Large 3 leads
Llama 4 Scout: 27.5 (#294), Mistral Large 3: 43.1 (#105)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1265 | 1413 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Mistral Large 3 leads
Llama 4 Scout: 37.0 (#261), Mistral Large 3: 60.0 (#101)
| Benchmark | Llama 4 Scout | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1279 | 1428 |
| LMArena Creative Writing | 1249 | 1386 |
| EQ-Bench Creative Writing | 783 | 1412 |
| LMArena Multi-Turn | 1280 | 1429 |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.7 on the Noometry Index. Llama 4 Scout costs 2.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Mistral Large 3?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Llama 4 Scout or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Mistral Large 3 share?
21 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Mistral Large 3 has 24.